paper-with-me

Papers

SubjectDrive: Scaling Generative Data in Autonomous Driving via Subject Control

2024-03-28 · Binyuan Huang, Yuqing Wen, Yucheng Zhao, Yaosi Hu, Yingfei Liu, Fan Jia, Weixin Mao, Tiancai Wang, Chi Zhang, Chang Wen Chen, Zhenzhong Chen, Xiangyu Zhang

Autonomous driving progress relies on large-scale annotated datasets. In this work, we explore the potential of generative models to produce vast quantities of freely-labeled data for autonomous driving applications and present SubjectDrive, the first model proven to scale generative data production in a way that could continuously improve autonomous driving applications. We investigate the impact of scaling up the quantity of generative data on the performance of downstream perception models and find that enhancing data diversity plays a crucial role in effectively scaling generative data production. Therefore, we have developed a novel model equipped with a subject control mechanism, which allows the generative model to leverage diverse external data sources for producing varied and useful data. Extensive evaluations confirm SubjectDrive's efficacy in generating scalable autonomous driving training data, marking a significant step toward revolutionizing data production methods in this field.

📄 PDF Abstract BibTeX arXiv:2403.19438

Code (0)

등록된 구현이 없습니다.

Tasks

Autonomous DrivingDiversity

Similar Papers 제목 키워드 기반

DriveWAM: Video Generative Priors Enable Scalable World-Action Modeling for Autonomous Driving

2026-05-27 · Chen Shi, Jinrui Xu, Shaoshuai Shi, Kehua Sheng 외 arxiv

Pretrained foundation models have become an important basis for end-to-end autonomous driving. In contrast to vision-language models pretrained primarily on static image-text pairs, video generative models capture tempor…

Scene UnderstandingAutonomous Driving

VaViM and VaVAM: Autonomous Driving through Video Generative Modeling

2025-02-21 · Florent Bartoccioni, Elias Ramzi, Victor Besnier, Shashanka Venkataramanan 외

We explore the potential of large-scale generative video models for autonomous driving, introducing an open-source auto-regressive video model (VaViM) and its companion video-action model (VaVAM) to investigate how video…

Autonomous DrivingImitation Learning

Copilot4D: Learning Unsupervised World Models for Autonomous Driving via Discrete Diffusion

2023-11-02 · Lunjun Zhang, Yuwen Xiong, Ze Yang, Sergio Casas 외

Learning world models can teach an agent how the world works in an unsupervised manner. Even though it can be viewed as a special case of sequence modeling, progress for scaling world models on robotic applications such …

Autonomous Driving

TrajDiff: End-to-end Autonomous Driving without Perception Annotation

2025-11-30 · Xingtai Gui, Jianbo Zhao, Wencheng Han, Jikai Wang 외 arxiv

End-to-end autonomous driving systems directly generate driving policies from raw sensor inputs. While these systems can extract effective environmental features for planning, relying on auxiliary perception tasks, devel…

Autonomous Driving

OpenLongTail: Generative Scaling of Long-Tail Driving Data

2026-07-10 · Lulin Liu, Nuo Chen, Yan Wang, Bangya Liu 외 arxiv

Scaling robust driving policies is fundamentally bottlenecked by the scarcity of edge cases in curated datasets. While the real world continuously captures these critical events, such long-tail events remain underutilize…

Autonomous Driving